动态上下文感知及残差注意力食管癌病变分割

doi:10.3778/j.issn.1002-8331.2408-0166

摘要/Abstract

摘要： 针对食管早癌及癌前病变区域细粒度分割中出现的类间差异小、类内差异大和边缘模糊等问题，提出一种动态上下文感知残差注意力网络。使用金字塔视觉Transformer v2（pyramid vision transformer v2，PVTv2）作为特征提取网络设计PVT分支，提取主要的特征表示，再通过残差块的堆叠设计残差注意力全卷积分支，对细节特征进行补充。在全卷积分支的编码器上设计动态残差注意力特征增强模块，在强化重要特征表示的同时，保留编码器每个阶段的初始图像信息。在PVT分支的解码阶段设计动态上下文特征感知引导模块，利用多尺度特征引导局部与全局信息的动态融合，实现自适应的渐进解码过程，在保留细节信息的同时，加深对全局上下文的理解。分别在自建食管癌数据集，公开数据集Kvasir-SEG、CVC-ClinicDB和ISIC2018上进行验证，实验结果表明，相似系数分别达到了74.92%、95.79%、96.83%和92.89%，优于主流分割网络。

关键词: 医学图像分割, 动态注意力, 跨尺度特征融合, 上下文感知

Abstract: A dynamic context-aware residual attention network is proposed to address small inter-class differences, large intra-class differences, and blurred edges in fine-grained segmentation of early esophageal cancer and precancerous lesions. The pyramid vision transformer v2 (PVTv2) is employed as the feature extraction network, forming the PVT branch to capture primary feature representations. A residual attention full convolution branch is designed by stacking residual blocks to enhance detailed features. A dynamic residual attention feature enhancement module is integrated into the encoder of this branch to reinforce key feature representations while preserving initial image information. During the decoding phase of the PVT branch, a dynamic context feature guidance module is designed to fuse local and global information using multi-scale features, enabling an adaptive progressive decoding process that retains details and enhances global context understanding. The validation on a self-built esophageal cancer dataset and public datasets Kvasir-SEG, CVC-ClinicDB, and ISIC2018 demonstrates Dice coefficients of 74.92%, 95.79%, 96.83% and 92.89%, respectively, outperforming mainstream segmentation networks.

Key words: medical image segmentation, dynamic attention, cross-scale feature fusion, context awareness

丁楠, 李小霞, 曹耀丹, 毛艳会, 何琴, 姜坤元, 程杰, 周颖玥. 动态上下文感知及残差注意力食管癌病变分割[J]. 计算机工程与应用, 2025, 61(22): 257-266.

DING Nan, LI Xiaoxia, CAO Yaodan, MAO Yanhui, HE Qin, JIANG Kunyuan, CHENG Jie, ZHOU Yingyue. Dynamic Context-Aware and Residual Attention Esophageal Cancer Lesion Segmentation[J]. Computer Engineering and Applications, 2025, 61(22): 257-266.

参考文献

[1] 赫捷, 陈万青, 李兆申, 等. 中国食管癌筛查与早诊早治指南(2022, 北京)[J]. 中国肿瘤, 2022, 31(6): 401-436.
HE J, CHEN W Q, LI Z S, et al. China guideline for the screening, early detection and early treatment of esophageal cancer(2022, Beijing)[J]. China Cancer, 2022, 31(6): 401-436.
[2] 宋颂, 雷林, 张瑞, 等. 食管癌筛查的研究进展[J]. 中华肿瘤防治杂志, 2022, 29(7): 451-455.
SONG S, LEI L, ZHANG R, et al. Research progress on screening for esophageal cancer[J]. Chinese Journal of Cancer Prevention and Treatment, 2022, 29(7): 451-455.
[3] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.
[4] 崔珂, 田启川, 廉露. 基于U-Net变体的医学图像分割算法综述[J]. 计算机工程与应用, 2024, 60(11): 32-49.
CUI K, TIAN Q C, LIAN L. Review of medical image segmentation algorithms based on U-Net variants[J]. Computer Engineering and Applications, 2024, 60(11): 32-49.
[5] FANG Y J, MUKUNDAN A, TSAO Y M, et al. Identification of early esophageal cancer by semantic segmentation[J]. Journal of Personalized Medicine, 2022, 12(8): 1204.
[6] ZHOU Z W, SIDDIQUEE M M R, TAJBAKHSH N, et al. UNet: redesigning skip connections to exploit multiscale features in image segmentation[J]. IEEE Transactions on Medical Imaging, 2020, 39(6): 1856-1867.
[7] GU Z W, CHENG J, FU H Z, et al. CE-net: context encoder network for 2D medical image segmentation[J]. IEEE Transactions on Medical Imaging, 2019, 38(10): 2281-2292.
[8] CAO H, WANG Y Y, CHEN J, et al. Swin-Unet: Unet-like pure transformer for medical image segmentation[C]//Proceedings of the 17th European Conference on Computer Vision. Cham: Springer, 2022: 205-218.
[9] LIU Z, LIN Y T, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2022: 9992-10002.
[10] CHEN J N, LU Y Y, YU Q H, et al. TransUNet: transformers make strong encoders for medical image segmentation[J]. arXiv:2102,04306, 2021.
[11] ZHANG Y D, LIU H Y, HU Q. TransFuse: fusing transformers and CNNs for medical image segmentation[C]//Proceedings of the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2021: 14-24.
[12] WANG W H, XIE E Z, LI X, et al. Pyramid vision transformer: a versatile backbone for dense prediction without convolutions[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2022: 548-558.
[13] WANG J F, HUANG Q M, TANG F L, et al. Stepwise feature fusion: local guides global[C]//Proceedings of the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2022: 110-120.
[14] SANDERSON E, MATUSZEWSKI B J. FCN-transformer feature fusion for polyp segmentation[C]//Proceedings of the 26th Annual Conference on Medical Image Understanding and Analysis. Cham: Springer, 2022: 892-907.
[15] JHA D, SMEDSRUD P H, RIEGLER M A, et al. Kvasir-SEG: a segmented polyp dataset[C]//Proceedings of the 26th International Conference on MultiMedia Modeling. Cham: Springer, 2020: 451-462.
[16] BERNAL J, SáNCHEZ F J, FERNáNDEZ-ESPARRACH G, et al. WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians[J]. Computerized Medical Imaging and Graphics, 2015, 43: 99-111.
[17] CODELLA N C F, GUTMAN D, CELEBI M E, et al. Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC)[C]//Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging. Piscataway: IEEE, 2018: 168-172.
[18] HUANG X H, DENG Z F, LI D D, et al. MISSFormer: an effective transformer for 2D medical image segmentation[J]. IEEE Transactions on Medical Imaging, 2023, 42(5): 1484-1494.
[19] AZAD R, HEIDARI M, SHARIATNIA M, et al. TransDeepLab: convolution-free transformer-based DeepLab v3+ for medical image segmentation[C]//Proceedings of the 5th International Workshop on Predictive Intelligence in Medicine. Cham: Springer, 2022: 91-102.
[20] RUAN J C, LI J C, XIANG S C. VM-UNet: vision mamba UNet for medical image segmentation[J]. arXiv:2402.02491, 2024.
[21] RAHMAN M M, SHOKOUHMAND S, BHATT S, et al. MIST: medical image segmentation transformer with convolutional attention mixing (CAM) decoder[C]//Proceedings of the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2024: 403-412.
[22] RAHMAN M M, MARCULESCU R. Multi-scale hierarchical vision transformer with cascaded attention decoding for medical image segmentation[C]//Proceedings of the 3rd International Conference on Medical Imaging with Deep Learning, 2023: 1526-1544.